© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 240
    Prev
    Next
    INDEX
    Explanations

    reading for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‘
    -1.58
    Because
    -1.33
     могут
    -1.30
    Usually
    -1.30
    Quite
    -1.28
    -{
    -1.27
    　　　　　　　　
    -1.27
    Another
    -1.27
     お
    -1.26
    {'
    -1.26
    POSITIVE LOGITS
     theses
    1.46
     '';
    1.42
     Erinnerungen
    1.37
     ร์
    1.32
     adopción
    1.30
     wła
    1.30
     škoda
    1.30
     Glaube
    1.29
     каждом
    1.27
     összefoglaló
    1.27
    Activations Density 0.038%

    No Known Activations